Menu
Skills neste repositório
O SkillsMP coletou 111 skills de randoneering/randoneering-agent-guide. Abra uma skill para revisar a origem e os detalhes.
randoneering/randoneering-agent-guideMostrando 40 de 111 skills coletadas.
Identifies error-prone APIs, dangerous configurations, and footgun designs that enable security mistakes. Use when reviewing API designs, configuration schemas, cryptographic library ergonomics, or evaluating whether code follows 'secure by default' and 'pit…
Idioma do texto original: inglês
Iteratively reviews and fixes Claude Code skill quality issues until they meet standards. Runs automated fix-review cycles using the skill-reviewer agent. Use to fix skill quality issues, improve skill descriptions, run automated skill review loops, or…
Idioma do texto original: inglês
Verifies code implements exactly what documentation specifies for blockchain audits. Use when comparing code against whitepapers, finding gaps between specs and implementation, or performing compliance checks for protocol implementations.
Idioma do texto original: inglês
Identifies dependencies at heightened risk of exploitation or takeover. Use when assessing supply chain attack surface, evaluating dependency health, or scoping security engagements.
Idioma do texto original: inglês
Builds and queries multi-language source code graphs for security analysis. Includes pre-analysis passes for blast radius, taint propagation, privilege boundaries, and entry point enumeration. Use when analyzing call paths, mapping attack surface, finding…
Idioma do texto original: inglês
Find similar vulnerabilities and bugs across codebases using pattern-based analysis. Use when hunting bug variants, building CodeQL/Semgrep queries, analyzing security vulnerabilities, or performing systematic code audits after finding an initial issue.
Idioma do texto original: inglês
Detects missing zeroization of sensitive data in source code and identifies zeroization removed by compiler optimizations, with assembly-level analysis, and control-flow verification. Use for auditing C/C++/Rust code handling secrets, keys, passwords, or…
Idioma do texto original: inglês
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Idioma do texto original: inglês
MUST USE when reviewing ClickHouse schemas, queries, or configurations. Contains 28 rules that MUST be checked before providing recommendations. Always read relevant rule files and cite specific rules in responses.
Idioma do texto original: inglês
Use when a user wants to deploy ClickHouse to the cloud, go to production, use ClickHouse Cloud, host a managed ClickHouse service, or migrate from a local ClickHouse setup to ClickHouse Cloud.
Idioma do texto original: inglês
Write, review, and improve blog posts for the Sentry engineering blog following Sentry's specific writing standards, voice, and quality bar. Use this skill whenever someone asks to write a blog post, draft a technical article, review blog content, improve a…
Idioma do texto original: inglês
Analyze a repository to generate recommended Claude Code settings.json permissions. Use when setting up a new project, auditing existing settings, or determining which read-only bash commands to allow. Detects tech stack, build tools, and monorepo structure.
Idioma do texto original: inglês
ALWAYS use this skill when creating or updating pull requests — never create or edit a PR directly without it. Follows Sentry conventions for PR titles, descriptions, and issue references. Trigger on any create PR, open PR, submit PR, make PR, update PR…
Idioma do texto original: inglês
Ansible automation, playbooks, and configuration management. Activate when working with Ansible YAML files or discussing Ansible patterns.
Idioma do texto original: inglês
Data governance & security analysis by generating SQL queries against Snowflake ACCOUNT_USAGE views. Use for: access control, audit trails, who accessed what, permissions, role hierarchies, PII/data classification, masking/row access policies, grants, tags,…
Idioma do texto original: inglês
Nix/NixOS package development, maintenance, and system configuration. Triggers: .nix, flake.nix, default.nix, nixpkgs, derivation, buildRustPackage, buildPythonPackage, NixOS modules. Covers package development, nixpkgs contributions, NixOS configuration,…
Idioma do texto original: inglês
PostgreSQL architecture and design patterns skill covering database schema design, partitioning strategies (range, list, hash, multi-level), high availability architectures (streaming replication, Patroni, failover), multi-tenancy models (shared schema,…
Idioma do texto original: inglês
Comprehensive PostgreSQL database engineering skill covering configuration tuning (postgresql.conf, memory, WAL, autovacuum), query optimization (EXPLAIN analysis, index design, rewriting patterns), cloud providers (AWS RDS, GCP Cloud SQL, Azure), database…
Idioma do texto original: inglês
Use when creating Python scripts that fetch data from REST APIs, when adding new API integrations, or when the user asks for help grabbing data from weather, IoT, or external services
Idioma do texto original: inglês
Python project workflow guidelines. Triggers: .py, pyproject.toml, uv, pip, pytest, Python. Covers package management, virtual environments, code style, type safety, testing, configuration, CQRS patterns, and Python-specific development tasks.
Idioma do texto original: inglês
Interactive testing of Cortex Agents. Use this when you want to test specific questions, debug responses, and explore agent behavior through hands-on exploration. For persisting results to formal evaluation datasets, use the dataset-curation skill.
Idioma do texto original: inglês
Establish a consistent protocol for tracking agent optimization work by organizing per-agent workspaces, versioned configuration snapshots, evaluation outputs, and a running optimization log.
Idioma do texto original: inglês
This skill contains best practices on how to write good system prompt/instructions. This is useful for tasks such as designing a prompt to automatically generate tool descriptions for semantic models in Snowflake Intelligence.
Idioma do texto original: inglês
This skill goes through a workflow for creating a new Cortex Agent with tools (Cortex Search Services and Semantic Views).
Idioma do texto original: inglês
Create and manage evaluation datasets for Cortex Agents. Use this to build datasets from scratch, from production data, or to add questions to existing datasets. Outputs datasets in the format required by Snowflake Agent Evaluations.
Idioma do texto original: inglês
Interactively debug specific agent query failures to identify and fix routing, SQL, or response issues. Use when investigating why a specific query fails or produces incorrect results, either from live testing or production event logs.
Idioma do texto original: inglês
Run formal evaluations on Cortex Agents using Snowflake's native Agent Evaluations. Use this to benchmark agent performance, measure accuracy metrics (correctness, tool_selection_accuracy, tool_execution_accuracy, logical_consistency), and compare…
Idioma do texto original: inglês
This goes through a workflow to guide AI assistants through optimizing Snowflake Cortex Agents for production readiness through systematic evaluation, improvement, and generalization. The process uses AI reasoning combined with human domain expertise to…
Idioma do texto original: inglês
"Use for optimizing existing Cortex Search services.
Idioma do texto original: inglês
Use for **ALL** requests that mention: create, build, set up, debug, fix, troubleshoot, optimize, improve, evaluate, or analyze a (Cortex) agent. This is the **REQUIRED** entry point - even if the request seems simple. DO NOT attempt to debug (Cortex) agents…
Idioma do texto original: inglês
Complete reference guide for Cortex Code (CoCo) CLI. Use when: learning cortex features, understanding commands, troubleshooting setup, exploring Snowflake tools, managing sessions, configuring agents, keyboard shortcuts, MCP integration. Triggers: how to use…
Idioma do texto original: inglês
Snowflake billing and credit analysis - generates SQL queries against ACCOUNT_USAGE billing/metering views to analyze Snowflake account charges and credit consumption (compute, storage, data transfer costs). Use for: virtual warehouse costs, credit…
Idioma do texto original: inglês
**[REQUIRED]** Use for ALL Streamlit tasks: creating, editing, debugging, beautifying, styling, theming, optimizing, or deploying Streamlit applications. Triggers: streamlit, st., dashboard, app.py, beautify, style, CSS, color, background, theme, button,…
Idioma do texto original: inglês
Building chat interfaces in Streamlit. Use when creating conversational UIs, chatbots, or AI assistants. Covers st.chat_message, st.chat_input, message history, and streaming responses.
Idioma do texto original: inglês
Building multi-page Streamlit apps. Use when creating apps with multiple pages, setting up navigation, or managing state across pages.
Idioma do texto original: inglês
Customizing Streamlit styling. Use for: theme colors, button styling, widget backgrounds, CSS customization. Covers config.toml, key= for CSS targeting, st.html(), .st-key-X selectors.
Idioma do texto original: inglês
Deploy Streamlit applications to Snowflake using the `snow` CLI tool. Covers snowflake.yml manifest configuration, compute pools, container runtime, and deployment workflow.
Idioma do texto original: inglês
Displaying charts, dataframes, and metrics in Streamlit. Use when visualizing data, configuring dataframe columns, or adding sparklines to metrics. Covers native charts, Altair, and column configuration.
Idioma do texto original: inglês
Optimizing Streamlit app performance. Use when apps are slow, rerunning too often, or loading heavy content. Covers caching, fragments, and static vs dynamic widget choices.
Idioma do texto original: inglês
Structuring Streamlit app layouts. Use when placing content in sidebars, columns, containers, or dialogs. Covers sidebar usage, column limits, horizontal containers, dialogs, and bordered cards.
Idioma do texto original: inglês